5,425 Hits in 4.6 sec

A Survey of Collaborative Reinforcement Learning: Interactive Methods and Design Patterns

Zhaoxing Li, Lei Shi, Alexandra I. Cristea, Yunzhan Zhou
2021 Designing Interactive Systems Conference 2021  
Recently, methods enabling humans and Artificial Intelligent (AI) agents to collaborate towards improving the efficiency of Reinforcement Learning -also called Collaborative Reinforcement Learning (CRL  ...  In this paper, we provide a long-term, in-depth survey, investigating human-AI collaborative methods based on both interactive reinforcement learning algorithms and human-AI collaborative frameworks, between  ...  A grand challenge of collaborative reinforcement learning is how human and AI communicate with each other.  ... 
doi:10.1145/3461778.3462135 fatcat:5f5ydpvp6fgkzmggxgs32sjdty

Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles [article]

Andrzej Cichocki, Alexander P. Kuleshov
2020 arXiv   pre-print
Future AI systems will be able not only to communicate with human users and each other, but also to efficiently exchange knowledge and wisdom with abilities of cooperation, collaboration and even co-creating  ...  Multi-agent systems such as these can be used to solve problems that would be difficult to solve by any individual intelligent agent.  ...  Categorization of the State-of the Arts Machine Learning Algorithms: Supervised, Unsupervised, Reinforcement Learning, Ensemble Learning, Deep Learning and Deep Reinforcement Learning (a) (b)  ... 
arXiv:2008.04793v4 fatcat:4l4wxa3bwnhlfbkfp2i63uwaou

Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning [article]

Yuchen Xiao, Xueguang Lyu, Christopher Amato
2021 arXiv   pre-print
Policy gradient methods have become popular in multi-agent reinforcement learning, but they suffer from high variance due to the presence of environmental stochasticity and exploring agents (i.e., non-stationarity  ...  ROLA allows each agent to learn an individual action-value function as a local critic as well as ameliorating environment non-stationarity via a novel centralized training approach based on a centralized  ...  Russell, “Robust multi-agent reinforcement learning via minimax deep deterministic policy gradient,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4213–4220  ... 
arXiv:2110.08642v3 fatcat:cgkvfeqzdjd6znwobewgarqct4

A Survey of Deep Reinforcement Learning in Video Games [article]

Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao
2019 arXiv   pre-print
Deep reinforcement learning (DRL) has made great achievements since proposed.  ...  single-agent to multi-agent.  ...  BiCNet [92] is a multi-agent deep reinforcement learning method to play StarCraft combat games.  ... 
arXiv:1912.10944v2 fatcat:fsuzp2sjrfcgfkyclrsyzflax4

Guest editorial: Collaborative intelligence for vehicular Internet of Things

Celimuge Wu, Kok-Lim Alvin Yau, Carlos Tavares Calafate, Lei Zhong
2021 China Communications  
Some collaborative learning approaches, such as federated learning and multi-agent systems, have been used to reduce network traffic and improve the learning efficiency of some smartphone applications.  ...  This feature topic focuses on the technical challenges and the synergistic effect of collaboration among heterogeneous entities and AI in enabling intelligent perception of the environment, intelligent  ...  Some collaborative learning approaches, such as federated learning and multi-agent systems, have been used to reduce network traffic and improve the learning efficiency of some smartphone applications.  ... 
doi:10.23919/jcc.2021.9495349 fatcat:3zybrihi4ze37lvmokf7yqjtlu

Cooperative Multi-Agent Interaction and Evaluation Framework Considering Competitive Networks with Dynamic Topology Changes

Jinbae Kim, Hyunsoo Lee
2020 Applied Sciences  
The proposed framework contributes to fast training process using multi-agent cooperation.  ...  In this paper, we propose a framework for learning the problems of competitive network topologies, wherein the environment dynamically changes agent, by computing the rewards via the system and via human  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10175828 fatcat:s5zprbasoncn3kuonx6224ghaq

Towards Controllable Agent in MOBA Games with Generative Modeling [article]

Shubao Zhang
2021 arXiv   pre-print
By modeling the control problem as an action generation process, we devise a deep latent alignment neural network model for training agent, and a corresponding sampling algorithm for controlling an agent's  ...  Both simulated and online experiments in the game Honor of Kings demonstrate the efficacy of the proposed methods.  ...  Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature.  ... 
arXiv:2112.08093v1 fatcat:hvykvhyyhjhdzcb6hwbcsto4sa

Universal Policies to Learn Them All [article]

Hassam Ullah Sheikh, Ladislau Bölöni
2019 arXiv   pre-print
We explore a collaborative and cooperative multi-agent reinforcement learning setting where a team of reinforcement learning agents attempt to solve a single cooperative task in a multi-scenario setting  ...  We propose a novel multi-agent reinforcement learning algorithm inspired by universal value function approximators that not only generalizes over state space but also over a set of different scenarios.  ...  Similar to single agent reinforcement learning, multi-agent reinforcement (MARL) is also producing break through results in challenging collaborative-competitive environments such as [OpenAI, 2018; Jaderberg  ... 
arXiv:1908.09184v1 fatcat:gpfuhvirpzgh7ont2a2mpklony

Applied Machine Learning for Games: A Graduate School Course [article]

Yilei Zeng, Aayush Shah, Jameson Thai, Michael Zyda
2021 arXiv   pre-print
In this paper, we describe our machine learning course designed for graduate students interested in applying recent advances of deep learning and reinforcement learning towards gaming.  ...  of game play.  ...  Gaming industry with exuberant data of in-game human collaborations makes suitable sand-box environments for conducting multi-agent interaction/collaboration research.  ... 
arXiv:2012.01148v2 fatcat:f44ln32jnbfhrearv234ylteru

A New Approach for Training Cobots from Small Amount of Data in Industry 5.0

Khalid Jabrane, Mohammed Bousmah
2021 International Journal of Advanced Computer Science and Applications  
In Industry 5.0, human-robot collaboration is a challenge for artificial intelligence (AI) and its subdomains. Indeed, integration of its domains is required.  ...  Machine learning is a vital part of today's world. Although the current Machine Learning slogan is "big data is required for a smarter AI".  ...   Scalability Scalability is a major issue in artificial intelligence when implementing multi-task learning via deep reinforcement learning [15] .  ... 
doi:10.14569/ijacsa.2021.0121070 fatcat:x46lmt7c7jacvge2bcmw7nelwq

Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training [article]

Piyush K. Sharma, Rolando Fernandez, Erin Zaroukian, Michael Dorothy, Anjon Basak, Derrik E. Asher
2021 arXiv   pre-print
Much work has been dedicated to the exploration of Multi-Agent Reinforcement Learning (MARL) paradigms implementing a centralized learning with decentralized execution (CLDE) approach to achieve human-like  ...  collaboration in cooperative tasks.  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory  ... 
arXiv:2107.14316v1 fatcat:n7qmmwwdenfbdngkmzflsqcx7y

Distributed Reinforcement Learning for Robot Teams: A Review [article]

Yutong Wang and Mehul Damani and Pamela Wang and Yuhong Cao and Guillaume Sartoretti
2022 arXiv   pre-print
The community has leveraged model-free multi-agent reinforcement learning (MARL) to devise efficient, scalable controllers for multi-robot systems (MRS).  ...  This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation.  ...  Springer Nature 2021 L A T E X template Distributed Reinforcement Learning for Robot Teams: A Review  ... 
arXiv:2204.03516v1 fatcat:iga6xlexmjbbflvuv5pjhifggy

Multi-agent modeling and simulation in the AI age

Wenhui Fan, Peiyu Chen, Daiming Shi, Xudong Guo, Li Kou
2021 Tsinghua Science and Technology  
Then we review the development status of the hybrid modeling and simulation combining multi-agent and system dynamics, the modeling and simulation of multi-agent reinforcement learning, and the modeling  ...  Wenhui Fan et al.: Multi-Agent Modeling and Simulation in the AI Age 609 2 Multi-Agent Modeling and Simulation 2.  ...  Multi-agent reinforcement learning In 2000, machine learning researchers took MAS as an important application background of AI [68] and proposed the concept of multi-agent learning in 2006 [69] .  ... 
doi:10.26599/tst.2021.9010005 fatcat:em72oiw5mvgc7lp3pjmch3n2eq

Multi-Agent Team Learning in Virtualized Open Radio Access Networks (O-RAN)

Pedro Enrique Iturria-Rivera, Han Zhang, Hao Zhou, Shahram Mollahasani, Melike Erol-Kantarci
2022 Sensors  
One unique aspect that motivates this paper is the availability of new opportunities that arise from using machine learning, more specifically multi-agent team learning (MATL), to optimize the RAN in a  ...  In this article, we first provide an overview of the landscape in RAN disaggregation, virtualization and O-RAN, then we present the state-of-the-art research in multi-agent systems and team learning as  ...  Sequential multi-agent deep reinforcement learning (SMADRL), Concurrent multiagent deep reinforcement learning (CMADRL) and Team multi-agent deep reinforcement learning (TMADRL) schemes. • SMADRL: In the  ... 
doi:10.3390/s22145375 pmid:35891055 pmcid:PMC9325199 fatcat:vssoevx23fhnfflevrg7oiyuim

Reward-Sharing Relational Networks in Multi-Agent Reinforcement Learning as a Framework for Emergent Behavior [article]

Hossein Haeri, Reza Ahmadzadeh, Kshitij Jerath
2022 arXiv   pre-print
We construct relational rewards as a function of the RSRN interaction weights to collectively train the multi-agent system via a multi-agent reinforcement learning algorithm.  ...  measure of how much one agent is invested in the success of (or 'cares about') another.  ...  Prior works may model this behavior via non-cooperative games.  ... 
arXiv:2207.05886v2 fatcat:n563qf34ffffbbjlsxoqfjgncy
« Previous Showing results 1 — 15 out of 5,425 results